使用 Bright Data MCP 和 OpenAI 的食谱推荐引擎
高级
这是一个Other, AI领域的自动化工作流，包含 23 个节点。主要使用 Set, Code, Wait, Function, McpClient 等节点，结合人工智能技术实现智能自动化。 基于 Bright Data MCP 和 OpenAI 4o mini 的食谱推荐引擎
前置要求
- •可能需要目标 API 的认证凭证
- •OpenAI API Key
使用的节点 (23)
工作流预览
可视化展示节点连接关系，支持缩放和平移
导出工作流
复制以下 JSON 配置到 n8n 导入，即可使用此工作流
{
"id": "3nPufqQQUzDzdo02",
"meta": {
"instanceId": "885b4fb4a6a9c2cb5621429a7b972df0d05bb724c20ac7dac7171b62f1c7ef40",
"templateCredsSetupCompleted": true
},
"name": "使用 Bright Data MCP 和 OpenAI 的食谱推荐引擎",
"tags": [],
"nodes": [
{
"id": "e1aeff42-0129-48df-b69b-927ef3e89f21",
"name": "当点击\"测试工作流\"时",
"type": "n8n-nodes-base.manualTrigger",
"position": [
-600,
145
],
"parameters": {},
"typeVersion": 1
},
{
"id": "50ddc2f7-89d1-4fb8-a47a-6b77ddb309da",
"name": "便签",
"type": "n8n-nodes-base.stickyNote",
"position": [
-200,
60
],
"parameters": {
"color": 4,
"width": 440,
"height": 320,
"content": "## 食谱数据抓取器"
},
"typeVersion": 1
},
{
"id": "da4a520e-0960-4262-af8e-82fb365546cb",
"name": "列出 Bright Data 的所有工具",
"type": "n8n-nodes-mcp.mcpClient",
"position": [
-380,
145
],
"parameters": {},
"credentials": {
"mcpClientApi": {
"id": "JtatFSfA2kkwctYa",
"name": "MCP Client (STDIO) account"
}
},
"typeVersion": 1
},
{
"id": "67dead27-adee-458e-9040-25aabf69c845",
"name": "设置食谱提取 URL",
"type": "n8n-nodes-base.set",
"position": [
-160,
145
],
"parameters": {
"options": {},
"assignments": {
"assignments": [
{
"id": "214e61a0-3587-453f-baf5-eac013990857",
"name": "url",
"type": "string",
"value": "https://realfood.tesco.com/search.html?search=tomato%20pasta&sortby=Rating"
},
{
"id": "45014942-0a2e-4f46-b395-f82f97bfa93e",
"name": "webhook_url",
"type": "string",
"value": "https://webhook.site/24878284-919d-4d39-bff0-5f36bfae17b6"
},
{
"id": "8d9b4ec0-416e-4b47-859a-36300f18aa23",
"name": "base_url",
"type": "string",
"value": "https://realfood.tesco.com/search.html"
}
]
}
},
"typeVersion": 3.4
},
{
"id": "e5d42bd3-2c23-42e6-be3b-c6e505cd585b",
"name": "分页数据提取",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
280,
145
],
"parameters": {
"text": "=Extract the paginated data from the provided content. \n\nHere's the content : {{ $json.result.content[0].text }}\n\nAppend the link with the Base URL as {{ $('Set the Recipe Extract URL').item.json.base_url }}",
"messages": {
"messageValues": [
{
"message": "You are an expert data miner"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"retryOnFail": true,
"typeVersion": 1.6
},
{
"id": "136c1487-4164-4b7e-b2ed-f9d29017f539",
"name": "遍历项目",
"type": "n8n-nodes-base.splitInBatches",
"position": [
876,
145
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "a10d507e-cd18-474f-998a-64f435b9d230",
"name": "输出分页信息数组的代码",
"type": "n8n-nodes-base.code",
"position": [
656,
145
],
"parameters": {
"jsCode": "return $input.first().json.output"
},
"typeVersion": 2
},
{
"id": "2047cdb3-ce19-4254-8d52-f99ec5101e18",
"name": "分页数据的结构化输出解析器",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
500,
380
],
"parameters": {
"jsonSchemaExample": "[{\n\t\"page_number\": \"page number in int\",\n\t\"link\": \"link to the web content\"\n}]"
},
"typeVersion": 1.2
},
{
"id": "4e912c2c-12a1-45ee-a821-9e1fd873120c",
"name": "用于食谱提取的 Bright Data MCP 客户端",
"type": "n8n-nodes-mcp.mcpClient",
"notes": "Scrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language.",
"position": [
60,
145
],
"parameters": {
"toolName": "scrape_as_html",
"operation": "executeTool",
"toolParameters": "={\n \"url\": \"{{ $json.url }}\"\n} "
},
"credentials": {
"mcpClientApi": {
"id": "JtatFSfA2kkwctYa",
"name": "MCP Client (STDIO) account"
}
},
"notesInFlow": true,
"typeVersion": 1
},
{
"id": "b14070b3-da81-4356-bef5-e70399893ce7",
"name": "循环内用于食谱提取的 Bright Data MCP 客户端",
"type": "n8n-nodes-mcp.mcpClient",
"notes": "Scrape a single webpage URL with advanced options for content extraction and get back the results in MarkDown language.",
"position": [
1480,
160
],
"parameters": {
"toolName": "scrape_as_html",
"operation": "executeTool",
"toolParameters": "={\n \"url\": \"{{ $json.link }}\"\n} "
},
"credentials": {
"mcpClientApi": {
"id": "JtatFSfA2kkwctYa",
"name": "MCP Client (STDIO) account"
}
},
"notesInFlow": true,
"typeVersion": 1
},
{
"id": "0577e0ca-162f-40bc-b96f-fbe5f9690826",
"name": "食谱数据提取的结构化输出解析器",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
1900,
360
],
"parameters": {
"schemaType": "manual",
"inputSchema": "{\n \"$schema\": \"http://json-schema.org/schema#\",\n \"title\": \"TescoRecipeSearchResults\",\n \"type\": \"object\",\n \"properties\": {\n \"pageTitle\": { \"type\": \"string\" },\n \"searchTerms\": { \"type\": \"string\" },\n \"sortBy\": { \"type\": \"string\" },\n \"numberOfResults\": { \"type\": \"integer\" },\n \"numberOfPages\": { \"type\": \"integer\" },\n \"numberOfFirstResult\": { \"type\": \"integer\" },\n \"numberOfLastResult\": { \"type\": \"integer\" },\n \"recipes\": {\n \"type\": \"array\",\n \"items\": {\n \"type\": \"object\",\n \"properties\": {\n \"title\": { \"type\": \"string\" },\n \"url\": { \"type\": \"string\" },\n \"category\": { \"type\": \"string\" },\n \"rating\": { \"type\": \"number\" },\n \"serves\": { \"type\": \"integer\" },\n \"dietaryOptions\": {\n \"type\": \"array\",\n \"items\": { \"type\": \"string\" }\n },\n \"isHealthy\": { \"type\": \"boolean\" }\n },\n \"required\": [\n \"title\",\n \"url\",\n \"category\",\n \"rating\",\n \"serves\",\n \"dietaryOptions\"\n ],\n \"additionalProperties\": false\n }\n }\n },\n \"required\": [\n \"pageTitle\",\n \"searchTerms\",\n \"sortBy\",\n \"numberOfResults\",\n \"numberOfPages\",\n \"numberOfFirstResult\",\n \"numberOfLastResult\",\n \"recipes\"\n ],\n \"additionalProperties\": false\n}\n"
},
"typeVersion": 1.2
},
{
"id": "dc24bede-a05a-45be-bea8-abd4efec5679",
"name": "创建二进制数据",
"type": "n8n-nodes-base.function",
"position": [
2200,
160
],
"parameters": {
"functionCode": "items[0].binary = {\n data: {\n data: new Buffer(JSON.stringify(items[0].json, null, 2)).toString('base64')\n }\n};\nreturn items;"
},
"typeVersion": 1
},
{
"id": "82630ed0-d321-42bd-ae68-e790228a61c7",
"name": "循环内数据提取的 Webhook 通知",
"type": "n8n-nodes-base.httpRequest",
"position": [
2120,
340
],
"parameters": {
"url": "={{ $('Set the Recipe Extract URL').item.json.webhook_url }}",
"options": {},
"sendBody": true,
"contentType": "multipart-form-data",
"bodyParameters": {
"parameters": [
{
"name": "recipe_content",
"value": "={{ $json.output.toJsonString() }}"
}
]
}
},
"typeVersion": 4.2
},
{
"id": "c2b53242-8c0d-49a4-8cdb-27da64377d50",
"name": "将结构化内容写入磁盘",
"type": "n8n-nodes-base.readWriteFile",
"position": [
2500,
160
],
"parameters": {
"options": {},
"fileName": "=d:\\Recipe-Structured-Data-{{ $('Loop Over Items').item.json.page_number }}.json",
"operation": "write"
},
"typeVersion": 1
},
{
"id": "f4eef0b9-8a1d-4eb2-92fc-7f4ee9d48898",
"name": "结构化食谱数据提取",
"type": "@n8n/n8n-nodes-langchain.chainLlm",
"position": [
1740,
160
],
"parameters": {
"text": "=Extract search data. Here's the content : \nOutput the data in JSON",
"messages": {
"messageValues": [
{
"message": "You are an expert data miner"
}
]
},
"promptType": "define",
"hasOutputParser": true
},
"retryOnFail": true,
"typeVersion": 1.6
},
{
"id": "bd64603d-230b-4318-b365-b186826454f0",
"name": "便签 2",
"type": "n8n-nodes-base.stickyNote",
"position": [
820,
-160
],
"parameters": {
"width": 440,
"height": 120,
"content": "## 免责声明"
},
"typeVersion": 1
},
{
"id": "3715be91-c809-495c-8a4e-ca58cf9de999",
"name": "便签1",
"type": "n8n-nodes-base.stickyNote",
"position": [
820,
0
],
"parameters": {
"color": 6,
"width": 1860,
"height": 540,
"content": "## 结构化数据提取"
},
"typeVersion": 1
},
{
"id": "c5d846da-581a-4182-a52d-0e29b302150e",
"name": "便签 3",
"type": "n8n-nodes-base.stickyNote",
"position": [
-680,
-340
],
"parameters": {
"width": 400,
"height": 320,
"content": "## 注意"
},
"typeVersion": 1
},
{
"id": "3af431fa-63fd-4140-8e86-8443a6ae013f",
"name": "便签6",
"type": "n8n-nodes-base.stickyNote",
"position": [
-200,
-240
],
"parameters": {
"color": 5,
"width": 440,
"height": 220,
"content": "## LLM 使用情况"
},
"typeVersion": 1
},
{
"id": "367bed09-cc77-4955-ada5-d71111bdfef1",
"name": "便签 5",
"type": "n8n-nodes-base.stickyNote",
"position": [
-680,
-780
],
"parameters": {
"color": 7,
"width": 400,
"height": 400,
"content": "## 徽标"
},
"typeVersion": 1
},
{
"id": "cbe55c76-4a62-4c15-af34-b49e037d779b",
"name": "用于分页数据提取的 OpenAI 聊天模型",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
280,
380
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "vPKynKbDzJ5ZU4cU",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
},
{
"id": "566f7f77-8eed-4ea2-9402-ccb46a13bf52",
"name": "用于结构化数据提取的 OpenAI 聊天模型",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
1700,
360
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "vPKynKbDzJ5ZU4cU",
"name": "OpenAi account"
}
},
"typeVersion": 1.2
},
{
"id": "fca8b6ce-a17c-416f-acc2-6a7a8bbf5b7b",
"name": "等待",
"type": "n8n-nodes-base.wait",
"position": [
1180,
160
],
"webhookId": "791cb0be-ba4a-417f-bcf2-ca8151bf16cd",
"parameters": {
"amount": 10
},
"typeVersion": 1.1
}
],
"active": false,
"pinData": {},
"settings": {
"executionOrder": "v1"
},
"versionId": "79bcb4d2-0dd7-4759-a2f6-7636f054d543",
"connections": {
"Wait": {
"main": [
[
{
"node": "Bright Data MCP Client For Recipe Extract Within The Loop",
"type": "main",
"index": 0
}
]
]
},
"Loop Over Items": {
"main": [
[],
[
{
"node": "Wait",
"type": "main",
"index": 0
}
]
]
},
"Create a binary data": {
"main": [
[
{
"node": "Write the structured content to disk",
"type": "main",
"index": 0
}
]
]
},
"Paginated Data Extract": {
"main": [
[
{
"node": "Code to output the array of paginated info",
"type": "main",
"index": 0
}
]
]
},
"Set the Recipe Extract URL": {
"main": [
[
{
"node": "Bright Data MCP Client For Recipe Extract",
"type": "main",
"index": 0
}
]
]
},
"List all tools for Bright Data": {
"main": [
[
{
"node": "Set the Recipe Extract URL",
"type": "main",
"index": 0
}
]
]
},
"Structured Recipe Data Extract": {
"main": [
[
{
"node": "Create a binary data",
"type": "main",
"index": 0
},
{
"node": "Webhook Notification for Data Extract Within the Loop",
"type": "main",
"index": 0
}
]
]
},
"When clicking ‘Test workflow’": {
"main": [
[
{
"node": "List all tools for Bright Data",
"type": "main",
"index": 0
}
]
]
},
"Write the structured content to disk": {
"main": [
[]
]
},
"Bright Data MCP Client For Recipe Extract": {
"main": [
[
{
"node": "Paginated Data Extract",
"type": "main",
"index": 0
}
]
]
},
"Code to output the array of paginated info": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Structured Output Parser for Paginated Data": {
"ai_outputParser": [
[
{
"node": "Paginated Data Extract",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"OpenAI Chat Model for Paginated Data Extract": {
"ai_languageModel": [
[
{
"node": "Paginated Data Extract",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"OpenAI Chat Model for Structured Data Extract": {
"ai_languageModel": [
[
{
"node": "Structured Recipe Data Extract",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Structured Output Parser for Recipe Data Extract": {
"ai_outputParser": [
[
{
"node": "Structured Recipe Data Extract",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Webhook Notification for Data Extract Within the Loop": {
"main": [
[
{
"node": "Loop Over Items",
"type": "main",
"index": 0
}
]
]
},
"Bright Data MCP Client For Recipe Extract Within The Loop": {
"main": [
[
{
"node": "Structured Recipe Data Extract",
"type": "main",
"index": 0
}
]
]
}
}
}常见问题
如何使用这个工作流？
复制上方的 JSON 配置代码，在您的 n8n 实例中创建新工作流并选择「从 JSON 导入」，粘贴配置后根据需要修改凭证设置即可。
这个工作流适合什么场景？
高级 - 其他, 人工智能
需要付费吗？
本工作流完全免费，您可以直接导入使用。但请注意，工作流中使用的第三方服务（如 OpenAI API）可能需要您自行付费。
相关工作流推荐
法律案例研究提取器，使用Bright Data MCP和Google Gemini的数据挖掘器
法律案例研究提取器，使用Bright Data MCP和Google Gemini的数据挖掘器
Set
Code
Wait
+10
22 节点Ranjan Dailata
人工智能
使用Bright Data和OpenAI 4o mini的自动化简历职位匹配引擎
Bright Data MCP与OpenAI 4o mini的自动化简历职位匹配引擎
Set
Function
Split Out
+10
22 节点Ranjan Dailata
人力资源
使用Bright Data和Google Gemini的Google Maps企业抓取和线索丰富
使用Bright Data和Google Gemini的Google Maps企业抓取和线索丰富工具
Set
Code
Wait
+11
29 节点Ranjan Dailata
潜在客户开发
使用Bright Data和OpenAI 4o mini进行DNB公司搜索与提取
基于Bright Data和OpenAI 4o mini的DNB公司搜索与提取
Set
Function
Mcp Client
+7
18 节点Ranjan Dailata
产品
AI代理驱动的ProductHunt数据提取和搜索（使用Bright Data和Google Gemini）
使用Bright Data MCP和Google Gemini AI提取和搜索ProductHunt数据
Set
Function
Mcp Client
+10
21 节点Ranjan Dailata
人工智能
使用Bright Data和OpenAI的Crunchbase B2B潜在客户发现管道
使用Bright Data、GPT-4o和Google Sheets从Crunchbase提取和总结B2B潜在客户
Set
Function
Http Request
+8
21 节点Ranjan Dailata
销售
工作流信息
难度等级
高级
节点数量23
分类2
节点类型13
作者
Ranjan Dailata
@ranjancseA Professional based out of India specialized in handling AI-powered automations. Contact me at ranjancse@gmail.com
外部链接
在 n8n.io 查看 →
分享此工作流